Agent skill · elithrar
add-skill
Create or update reusable Agent Skills for Codex, ChatGPT, Claude, OpenCode, and other compatible hosts. Use when defining a SKILL.md trigger boundary, workflow, supporting resources, metadata, or activation and output evals.
What it needs
About 3k tokens when loaded.
What this skill does
Creating Agent Skills Create skills for reusable, task-specific workflows that need procedural guidance, domain knowledge, tools, or packaged resources. Use AGENTS.md for durable repository conventions and prompt or thread context for one-off instructions. Do not create a skill merely to restate behavior the host already provides reliably. Treat every skill as a behavioral artifact: define its activation boundary, intended behavior, evidence of success, and safe failure behavior. Workflow 1. Resolve the target hosts, installation scope, expected user requests, non-trigger near misses, dependencies, and safety boundaries. 2. For an existing skill, read its complete SKILL.md and directly referenced resources before proposing changes. 3. Identify the smallest reusable workflow and decide whether instructions alone are sufficient. 4. Add references/ for on-demand knowledge, scripts/ for repeated deterministic work, and assets/ only for files used in outputs. 5. Write a concise description that distinguishes this skill from adjacent skills. 6. Define expected inputs, workflow steps, outputs, unsupported inferences, and ask, stop, or fallback conditions. 7. Validate the skill against the target host or specification. 8. Test activation and task behavior with representative positive, negative, incomplete, and edge cases. Structure Portable Agent Skills require SKILL.md with name and description. Keep host-specific metadata outside the portable core when possible. name: 1-64 lowercase letters, digits, and hyphens; match the directory name. description: 1-1024 characters; state what the skill does and when to use it. agents/openai.yaml: Optional Codex and ChatGPT UI metadata, invocation policy, and tool dependencies. evals/: Harness-specific evaluation fixtures, not part of the portable skill format. For widest Codex and ChatGPT compatibility, keep frontmatter to name and description unless the target host explicitly supports additional fields. Keep SKILL.md concise. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills elithrar/add-skill